← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M2 Max (30c) · 32 GB · 4bit · 2026-04-28

Performance

8k

tokens

618.3

PP tok/s

63.2

TG tok/s

13248

TTFT (ms)

21.5

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 32 GB

GPU Cores 30

Software

oMLX v0.3.8.dev3

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	614.6	69.0	21.2 GB	view
8k	618.3	63.2	21.5 GB	current
16k	594.3	54.0	22.2 GB	view
32k	537.2	41.1	23.5 GB	view